Image processing techniques are now commonly used in the medical field for early detection of diseases. This research aims to improve accuracy, sensitivity and specificity of early detection of lung cancer through a combination of image processing techniques and data mining. The Computed Tomography (CT) scan image of the lungs is pre-processed and the Region of Interest (ROI) segmented, retained and compressed using a DWT (Discrete Waveform Transform) technique. The resulting ROI image is decomposed into four sub frequencies, bands LL, HL, LH, and HH. Again, the LL sub frequency is decomposed into four sub-bands, applying a 2-level DWT to the ROI based image. Further, features such as entropy, co-relation, energy, variance and homogeneity are extracted from the 2-level DWT images using a GLCM (Gray level Co-occurrence Matrix) with classification effected by means of an SVM (Support Vector Machine). Classification identifies whether the CT image is normal or cancerous. The Lung Image Database Consortium dataset (LIDC) has been used for training and testing purpose for this study. A Receiver Operating Characteristics (ROC) curve is used to analyze the performance of the system. Overall the system has accuracy of 95.16%, sensitivity of 98.21% and specificity of 78.69%.