Brain tumors amount to less than 2% of all malignant neoplasms. However, they account for approximately 20% of all childhood cancers and are the leading cause of cancer mortality among children. Recently, enormous progress has been achieved in the field of pediatric neuro-oncology regarding the classification of children's brain tumors, as well as the understanding of the genetic events involved in their pathogenesis; thus leading to an emerging role of molecular diagnostic approaches using novel tools. Comparative genomic hybridization (CGH) is a technique that has revolutionized cytogenetic knowledge in the past decade. It permits the detection of chromosomal copy number changes without the need for cell culturing and gives a global overview of chromosomal gains and losses throughout the whole genome of a tumor. A survey of CGH-related publications on central and peripheral nervous system tumors in the pediatric and adolescent population revealed 884 cases. The CNS tumor groups most frequently examined by CGH were embryonal tumors (268 cases/30.3%) and ependymomas (241/27.2%), followed by astrocytic (163/18.4%), peripheral nerve (73/8.2%), choroid plexus tumors (56/6.3%), and craniopharyngiomas (38/4.3%). The most common CNS tumor entities were medulloblastomas (238/26.9%), classic ependymomas (160/18.1%), anaplastic ependymomas (70/7.9%), pleomorphic xanthoastrocytomas (53/6.0%), and pilocytic astrocytomas (50/5.6%). This article provides a short review of the CGH technique and its pitfalls, summarizes the current CGH-related data on pediatric brain tumors and muses on the future of CGH.