Inclusion Criteria:

• Patients must have histologically confirmed carcinoma of the gallbladder, intrahepatic or extrahepatic biliary tract, not amenable to resection with curative intent.
• Patients must have measurable disease as per the modified RECIST criteria, defined as at least one lesion that can be accurately measured in at least one dimension, with minimum lesion size equal to or more than twice the slice thickness of the imaging study used.
• Patients who are previously untreated as well as those who have received prior therapy are eligible to participate in this study. Patients may have received up to a total of two prior chemotherapy regimens for their disease, including biologic therapy(ies). The same regimen may have been received at different times during the course of the patient's treatment. Surgery, radiofrequency ablation, external beam radiotherapy, or other directed therapies do not count as prior regimens and are allowed.
• Previous treatment may include systemic chemotherapy, however, prior capecitabine (unless administered as a radiosensitizing agent concurrently with prior external beam radiotherapy) or oxaliplatin are excluded.
• If radiation was previously received, the measurable disease must be recurrent or metastatic disease outside the previous radiation field.
• A minimum of 4 weeks must have elapsed since completion of any prior chemotherapy or radiotherapy.
• Patients should have a life expectancy of at least 16 weeks based on the clinical judgment of the Investigator.
• ECOG Performance Status of </= 2 or Karnofsky > 70.
• Adequate bone marrow function defined as absolute peripheral granulocyte count of >/= 1500/mm3, platelet count >/= 100,000/ mm3, and hemoglobin >/= 10 gm/dL.
• Adequate renal function, defined as serum creatinine </= 1.5 X ULN institutional normal and calculated creatinine clearance >30 mL/min (using Cockcroft and Gault formula-Appendix B).
• Patients must have adequate hepatic function: total bilirubin </= 2.0 gm/dL; serum albumin >/= 2.5 gm/dL; transaminases up to 5 X the upper limit of institutional normal value; or prothrombin time prolonged up to 2 seconds greater than the institutional normal value.
• Negative serum pregnancy test in women with childbearing potential.
• The effects of the combination of oxaliplatin and capecitabine on the developing fetus are unknown. For this reason, women of childbearing potential and men must agree to use adequate contraception (hormonal or barrier method of birth control) prior to study entry and for the duration of study participation. Should a woman become pregnant while participating in this study, she should inform her treating physician immediately.
• Patients must sign an Informed Consent and Authorization indicating that they are aware of the investigational nature of this study and the known risks involved. The consent form appended to this protocol must be used to document patient consent.
• Age >/=18 years.
• Patients taking therapeutic dose-levels of coumarin-derivate anticoagulants should be switched to low LMWH.

Low-dose coumadin (e.g. 1 mg po per day) in patients with in-dwelling venous access devices, is allowed.

Exclusion Criteria:

• Prior therapy with oxaliplatin or capecitabine; capecitabine administered as a radiosensitizing agent concurrently with prior external beam radiotherapy is allowable.
• Patients who have had chemotherapy within 4 weeks (6 weeks for nitrosoureas or Mitomycin C) prior to entering the study or those who have not recovered from adverse events due to agents administered more than 4 weeks earlier.
• Patients may not be receiving any other investigational agents nor have received any investigational drug </= 30 days prior to enrollment.
• Patients with known brain metastases should be excluded from this clinical trial because of their poor prognosis and because they often develop progressive neurologic dysfunction that would confound the evaluation of neurologic and other adverse events.
• Gastrointestinal tract disease resulting in an inability to take oral medication or a requirement for IV alimentation, prior surgical therapy affecting absorption.
• Uncontrolled intercurrent illness including, but not limited to, ongoing or active infection, symptomatic congestive heart failure, unstable angina pectoris, cardiac arrhythmia, or psychiatric illness/social situations that would limit compliance with study requirements.
• Because patients with immune deficiency are at increased risk of lethal infections when treated with marrow-suppressive therapy, HIV-positive patients receiving combination anti-retroviral therapy are excluded from the study because of possible pharmacokinetic interactions with XELOX. Appropriate studies will be undertaken in patients receiving combination anti-retroviral therapy when indicated.
• Patients with extensive symptomatic fibrosis of the lungs.
• Peripheral neuropathy > grade 1.
• Known DPD deficiency.
• Patients receiving therapeutic doses of coumarin-derivative anticoagulant therapy are excluded since a drug interaction between capecitabine and coumarin anticoagulants has been reported. Patients requiring anticoagulation who may be safely switched to LMWH are eligible.