Health and medical big data come from a variety of sources, including administrative databases, clinical trials, electronic health records (EHRs), patient registries, genomic, and other ‘omic measurements and medical imaging. More recently, data are being integrated from social media, wearable and implantable devices, mobile applications, occupational and retail information and environmental monitoring. These data are ‘big’ in volume because they include large numbers of records (e.g. administrative data), large numbers of variables (e.g. ‘omics data), or both (e.g. EHRs). They are also characterised by great variety (including both structured data and unstructured data such as free text and images) and high velocity (generated in or near real-time). Health and medical big data present vast potential for the discovery of relationships among pieces of information that would not previously have been possible. This requires integrating data-driven and hypothesis-driven approaches, and deductive and inductive reasoning, and applying new and up-scaled analytic methods that draw on both statistics and computer science. It is time for epidemiologists to embrace this challenge!