The Content-Based Image Retrieval (CBIR) has received great attention in the medical community because it is capable of retrieving similar images that have known pathologies. However, the sheer volume of data produced in radiology centers has precluded the use of CBIR in the daily routine of hospitals. The volume of medical images produced in medical centers has increased fast. The annual data produced from exams in the big radiology centers is greater than 10 Terabytes. Therefore, we have reached to an unprecedented age of "BigData". We here present a bag-of task approach to speed up the images retrieval of lung nodules stored in a large medical images database. This solution combines texture attributes and registration algorithms that together are capable of retrieving images of benign lung nodules with greater-than-72% precision and greater-than-67% in malignant cases, yet running in a few minutes over the Grid, making it usable in the clinical routine.