Co-locating the gross tumour volume (GTV) on cone-beam computed tomography (CBCT) of non small cell lung cancer (NSCLC) patients receiving radiotherapy (RT) is difficult because of the lack of image contrast between the tumour and surrounding tissue. This paper presents a new image analysis approach, based on second-order statistics obtained from gray level co-occurrence matrices (GLCM) combined with level sets, for assisting clinicians in identifying the GTV on CBCT images. To demonstrate the potential of the approach planning CT images from 50 NSCLC patients were rigidly registered with CBCT images from fractions 1 and 10. Image texture analysis was combined with two level set methodologies and used to automatically identify the GTV on the registered CBCT images. The Dice correlation coefficients (μ± σ) calculated between the clinician-defined and image analysis defined GTV on the planning CT and the CBCT for three different parameterisations of the model were: 0.69 ± 0.19, 0.63 ± 0.17, 0.86 ± 0.13 on fraction 1 CBCT images and 0.70 ± 0.17, 0.62 ± 0.15, 0.86 ± 0.12 on fraction 10 CBCT images. This preliminary data suggests that the image analysis approach presented may have potential for clinicians in identifying the GTV in low contrast CBCT images of NSCLC patients. Additional validation and further work, particularly in overcoming the lack of gold standard reference images, are required to progress this approach.