OBJECTIVE To evaluate the performance of two deformable registration softwares (a commercial and an open source software) using cone-beam computed tomography (CBCT) images. METHODS We used a set of 34 lung patients with generally large tumors each having between 1 and 20 CBCT scans. A radiation oncologist resident contoured GTVs on each CBCTs using planning CT contours as reference. Deformable registrations were performed on CT scans to adapt it to the first CBCT of each patient independently with both software. Then each CBCT was registered to the next CBCT. Contour structures have been deformed in the process for the commercial software and for the open source software contours have been drawn manually on deformed images. RESULTS Mean remaining volume (±SD) for manual GTV contours was 59 ± 32 %. GTVs obtained with the open source software were closer to the manual GTV in size than the commercial software. Mean relative errors on volume were 45 ± 60 % for the commercial system (33 patients) and 9 ± 2 % for the open source software (6 patients). Relative errors for the commercial software increased exponentially with the volume reduction but were constant over all CBCT for the open source software. Mean Jaccard and Dice's index were 0.57 and 0.71 for the commercial software (24 patients) and 0.80 and 0.88 for the open source software (6 patients). CONCLUSIONS Open source software shown tendency to give better results than commercial software but was slower than the commercial software.