While many computer-aided detection (CADe) systems for CT colonography can detect polypoid lesions at a high sensitivity level, very few are targeted toward detecting flat lesions. Research has shown that flat lesions are more likely to contain carcinoma than polypoid lesions; therefore, it is imperative that they be adequately detected in screenings and examinations. However, current CADe systems systems have a low sensitivity for flat lesions, with a relatively high false-positive (FP) rate. By generating a surface mesh of the colon and spinning a tangent line at each point of the mesh, we have developed a new CADe system for detecting flat lesions. With our system, we detected 82% (23/28) of flat lesions in our dataset with a small number of FPs (4.5 per patient), whereas a modified shape-index-based CADe system detected 68% (19/28) of them with 10 FPs per patient.