Lung cancer is the cause of one of the most common cancer-related deaths found in both males and females. Although attention has been paid to early stage predictions and diagnoses, prognosis is not at all working good. The two major challenges in nodule detection are to detect nodules that overlap with ribs and clavicles and also to reduce the number of false positives caused by these structures. This problem can be approached by developing more sensitive diagnosis methods using the new growing neural network technologies. In most of the existing CAD schemes for lung cancer detection by detecting the lung nodules they are not able to detect the nodules that overlap with ribs and clavicles, even though there exists VDE based CAD schemes(MTANN) with better sensitivity when compared with other schemes, it is not enough to provide high sensitivity. Here a CAD scheme incorporated with VDE scheme with FFNN that can provide better sensitivity compared to the existing techniques. This method is found to possess a sensitivity of 92.3% which is better.